Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Mar 29, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.3K

Emergency Operation Scheme Generation for Urban Rail Transit Train Door Systems Using Retrieval-Augmented Large

Lu Huang1,2, Zhigang Liu1, Chengcheng Yu2

  • 1School of Urban Railway Transportation, Shanghai University of Engineering Science, Shanghai 201620, China.

Sensors (Basel, Switzerland)
|March 28, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

MIL-61 and Eu<sup>3+</sup>@MIL-61 as Signal Transducers To Construct an Intelligent Boolean Logical Library Based on Visualized Luminescent Metal-Organic Frameworks.

ACS applied materials & interfaces·2019
Same author

Stem Cell-Derived Exosomes Prevent Aging-Induced Cardiac Dysfunction through a Novel Exosome/lncRNA MALAT1/NF-<i>κ</i>B/TNF-<i>α</i> Signaling Pathway.

Oxidative medicine and cellular longevity·2019
Same author

Human umbilical cord mesenchymal stem cell derived exosomes encapsulated in functional peptide hydrogels promote cardiac repair.

Biomaterials science·2019
Same author

Carbohydrate metabolism genes dominant in a subtropical marine mangrove ecosystem revealed by metagenomics analysis.

Journal of microbiology (Seoul, Korea)·2019
Same author

The Diagnostic Value of 3D Power Doppler Ultrasound Combined With VOCAL in the Vascular Distribution of Breast Masses.

Academic radiology·2019
Same author

Is hysterectomy beneficial in radical cystectomy for female patient with urothelial carcinoma of bladder? A retrospective analysis of consecutive 112 cases from a single institution.

BMC urology·2019

This study introduces a retrieval-augmented large language model (LLM) framework to generate adaptable emergency operation schemes (EOSs) for urban rail transit (URT) train doors. The system improves scheme executability and traceability using evidence-based data.

Area of Science:

  • Artificial Intelligence
  • Transportation Engineering
  • Safety Science

Background:

  • Urban rail transit (URT) train-door failures are safety-critical, causing service disruptions.
  • Existing emergency operation schemes (EOSs) are static, difficult to adapt, and hard to verify.
  • Need for dynamic, verifiable, and evidence-traceable EOS generation.

Purpose of the Study:

  • Propose a retrieval-augmented large language model (LLM) framework for executable and evidence-traceable EOS generation.
  • Improve adaptability and verifiability of safety-critical operation schemes.
  • Address limitations of static EOSs in evolving fault patterns.

Main Methods:

  • Normalize multi-source heterogeneous incident evidence into a structured representation.
Keywords:
human–machine collaborationincident responseknowledge baseretrieval and rerankingsafety-critical decision supporttrain door faultsurban rail transit

Related Experiment Videos

Last Updated: Mar 29, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.3K
  • Employ a hybrid retriever (dense + BM25) with cross-encoder reranking for evidence selection.
  • Fine-tune a generator with structured objectives for schema compliance, role assignment, and citation grounding.

    • Main Results:

    • Hybrid retriever with reranking achieved high retrieval quality (Recall@5 = 0.78).
    • The full LLM framework significantly improved operational usability metrics (SchemaPass = 0.88, RoleAcc = 0.91, CiteCov = 0.73, UsableAns = 0.83).
    • Outperformed pure LLM baseline (UsableAns = 0.15) and RAG-only prompting (UsableAns = 0.26).

    Conclusions:

    • Combining high-utility retrieval with structure- and citation-aware fine-tuning enhances EOS executability and verifiability.
    • The proposed framework offers a substantial improvement for safety-critical operation scheme generation in URT.
    • Demonstrates the potential of LLMs for dynamic and reliable safety management in critical infrastructure.